# Image-Text Pre-Training for Logo Recognition

arXiv: https://arxiv.org/abs/2309.10206 · HTML: https://mlsanity.com/paper/2309.10206/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 18 Sep 2023.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [TAP: Text-Aware Pre-training for Text-VQA and Text-Caption](https://mlsanity.com/paper/2012.04638/) (2020)
- [Spatially Aware Multimodal Transformers for TextVQA](https://mlsanity.com/paper/2007.12146/) (2020)
- [LogoDet-3K: A Large-Scale Image Dataset for Logo Detection](https://mlsanity.com/paper/2008.05359/) (2020)
- [Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps](https://mlsanity.com/paper/2012.05153/) (2020)
- [Open Set Logo Detection and Retrieval](https://mlsanity.com/paper/1710.10891/) (2017)
- [Open Logo Detection Challenge](https://mlsanity.com/paper/1807.01964/) (2018)
- [Deep Learning for Logo Recognition](https://mlsanity.com/paper/1701.02620/) (2017)
- [Scalable Logo Recognition using Proxies](https://mlsanity.com/paper/1811.08009/) (2018)
- [Large Scale Open-Set Deep Logo Detection](https://mlsanity.com/paper/1911.07440/) (2019)

## Built on by (most cited first, 2 of 2)

- [CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classification](https://mlsanity.com/paper/2401.06194/) (2024)
- [Self-Supervised Learning for Text Recognition: A Critical Survey](https://mlsanity.com/paper/2407.19889/) (2024)

## Abstract (arXiv)

Open-set logo recognition is commonly solved by first detecting possible logo regions and then matching the detected parts against an ever-evolving dataset of cropped logo images. The matching model, a metric learning problem, is especially challenging for logo recognition due to the mixture of text and symbols in logos. We propose two novel contributions to improve the matching model's performance: (a) using image-text paired samples for pre-training, and (b) an improved metric learning loss function. A standard paradigm of fine-tuning ImageNet pre-trained models fails to discover the text sensitivity necessary to solve the matching problem effectively. This work demonstrates the importance of pre-training on image-text pairs, which significantly improves the performance of a visual embedder trained for the logo retrieval task, especially for more text-dominant classes. We construct a composite public logo dataset combining LogoDet3K, OpenLogo, and FlickrLogos-47 deemed OpenLogoDet3K47. We show that the same vision backbone pre-trained on image-text data, when fine-tuned on OpenLogoDet3K47, achieves 98.6% recall@1, significantly improving performance over pre-training on Imagenet1K (97.6%). We generalize the ProxyNCA++ loss function to propose ProxyNCAHN++ which incorporates class-specific hard negative images. The proposed method sets new state-of-the-art on five public logo datasets considered, with a 3.5% zero-shot recall@1 improvement on LogoDet3K test, 4% on OpenLogo, 6.5% on FlickrLogos-47, 6.2% on Logos In The Wild, and 0.6% on BelgaLogo.